English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Currently, detecting 3D objects in Bird's-Eye-View (BEV) is superior to other3D detectors for autonomous driving and robotics. However, transforming imagefeatures into BEV necessitates special operators to conduct feature sampling.These operators are not supported on many edge devices, bringing extraobstacles when deploying detectors. To address this problem, we revisit thegeneration of BEV representation and propose detecting objects in perspectiveBEV -- a new BEV representation that does not require feature sampling. Wedemonstrate that perspective BEV features can likewise enjoy the benefits ofthe BEV paradigm. Moreover, the perspective BEV improves detection performanceby addressing issues caused by feature sampling. We propose PersDet forhigh-performance object detection in perspective BEV space based on thisdiscovery. While implementing a simple and memory-efficient structure, PersDetoutperforms existing state-of-the-art monocular methods on the nuScenesbenchmark, reaching 34.6% mAP and 40.8% NDS when using ResNet-50 as thebackbone.

PersDet: Monocular 3D Detection in Perspective Bird's-Eye-View